Vehicle collisions amount to a significant loss of life in America. Upward of 30,000 lives are lost each year in the United States alone. Hundreds of millions of dollars are spent each year on vehicle safety and roadway design in the United States, and many studies have been conducted on the causal factors for vehicle collisions. This study used artificial neural networks as a means to predict the occurrence of injury of a vehicle collision. The objective was to classify the levels of the “injury occurrence” in vehicle collisions, given certain input variables, including demographic and environmental factors involved in crashes. Using Neural Ware's Predict software, a back‐propagation neural network model was constructed, trained, tested, and validated using data from the 2006 and 2007 Florida Traffic Crash Database. The neural network's computational power was iteratively increased by adding hidden layers to boost its predicting power until the performance began to plateau. Classification rates as well as Kolmogorov‐Smirnov (K‐S) statistical analysis were used to validate the model. A sensitivity analysis was then applied to find the level of contribution that the input variables had on the injury occurrence. Accident severity, number of lanes, and road surface conditions were found to have the most positive impacts on the injury occurrence. The implications of the study are discussed at the end of the article.

Vehicle collisions amount to a significant loss of life in America. This study used artificial neural networks as a means to predict the occurrence of injury of a vehicle collision. Using Neural Ware’s Predict software a neural network structure was trained, tested, and validated using data from the 2006 and 2007 Florida Traffic Crash Database. The objective was to assess whether or not properly designed neural network architecture could adequately classify the levels of the “Injury Occurrence” output variable, given certain inputs such as demographic and environmental factors involved in crashes. A Kolmogorov-Smirnov statistical analysis was employed to objectively assess whether or not the neural network properly classified the levels of Injury Occurrence and to what extent. The artificial network’s computational power was iteratively increased by adding hidden layers thus boosting its performance. a sensitivity analysis was used to find the level of contribution the input variables had on the “Injury Occurrence” output variable. Top three positive and negative most impacting factors were identified and the implications were discussed at the end of the paper.

No abstract